EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable Machine Learning for Compressive Strength Prediction of Fly Ash-Based Geopolymer Concrete

Farnaz Ahadian, Ümit Işıkdağ, Gebrail Bekdaş, Sinan Melih Nigdeli, Celal Cakiroglu, Zong Woo Geem

Sustainability · 25.02.2026 · 18 (5) · 2227

DOI: 10.3390/su18052227 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 25.02.2026. Verfasst von Farnaz Ahadian und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fly ash-based geopolymer concrete (GPC) is a sustainable alternative to conventional cementitious materials; however, its compressive strength is governed by complex and highly correlated mixture parameters, making experimental optimization expensive and data-driven modeling challenging. While machine learning (ML) techniques have been widely applied to predict GPC strength, most studies prioritize predictive accuracy without explicitly addressing multicollinearity among input variables, which can distort feature importance, reduce model stability, and limit engineering interpretability. This study proposes a multicollinearity-integrated and interpretable ML framework that systematically embeds correlation diagnostics and structured feature screening within the modeling pipeline rather than treating interpretability as a post-processing step. Multiple conventional and ensemble learning algorithms were comparatively evaluated using cross-validation to ensure generalization robustness. The proposed framework achieved a maximum coefficient of determination (R2) of 0.96 with low prediction error, outperforming baseline regression models while demonstrating improved stability under correlated input conditions. Unlike existing studies that rely solely on black-box optimization, the integrated interpretability analysis revealed physically consistent dominance of curing temperature, alkali content, and water-related parameters in governing strength development. By explicitly coupling predictive performance with multicollinearity mitigation and engineering-oriented interpretability, this work advances beyond accuracy-driven ML applications and provides a robust and transparent decision-support tool for sustainable geopolymer mix design.

Zitieren

APA

Ahadian, F., Işıkdağ, Ü., Bekdaş, G., Nigdeli, S. M., Cakiroglu, C., & Geem, Z. W. (2026). Interpretable Machine Learning for Compressive Strength Prediction of Fly Ash-Based Geopolymer Concrete. Sustainability, 18(5), 2227. https://doi.org/10.3390/su18052227

Vancouver

Ahadian F, Işıkdağ Ü, Bekdaş G, Nigdeli SM, Cakiroglu C, Geem ZW. Interpretable Machine Learning for Compressive Strength Prediction of Fly Ash-Based Geopolymer Concrete. Sustainability. 2026;18(5):2227. doi:10.3390/su18052227

BibTeX
@article{Ahadian2026,
  author = {Ahadian, Farnaz and Işıkdağ, Ümit and Bekdaş, Gebrail and Nigdeli, Sinan Melih and Cakiroglu, Celal and Geem, Zong Woo},
  title = {Interpretable Machine Learning for Compressive Strength Prediction of Fly Ash-Based Geopolymer Concrete},
  journal = {Sustainability},
  year = {2026},
  volume = {18},
  number = {5},
  pages = {2227},
  doi = {10.3390/su18052227}
}
Kostenlos starten →